Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hunting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ÑĦоÑĢ
    -0.27
    ijd
    -0.27
    ars
    -0.26
     _$
    -0.26
    &_
    -0.26
    宫殿
    -0.26
    &B
    -0.26
    flush
    -0.26
    åıijçĶŁ
    -0.26
     flush
    -0.25
    POSITIVE LOGITS
     nudity
    0.29
    è¾Ĺ转
    0.28
     blow
    0.27
     transit
    0.26
    ÑĥеÑĤ
    0.25
    .zip
    0.25
     necessities
    0.25
     blowing
    0.24
     dele
    0.24
    mland
    0.24
    Act Density 0.011%

    No Known Activations